bioroebe 0.10.80

data/lib/bioroebe/taxonomy/node.rb

@@ -0,0 +1,118 @@
+#!/usr/bin/ruby -w
+# Encoding: UTF-8
+# frozen_string_literal: true
+# =========================================================================== #
+# === Bioroebe::Taxonomy::Node
+#
+# This class represents a Node.
+# =========================================================================== #
+require 'bioroebe/base/commandline_application/commandline_application.rb'
+
+module Bioroebe
+
+module Taxonomy
+
+class Node < ::Bioroebe::CommandlineApplication # === Bioroebe::Taxonomy::Node
+
+  # ========================================================================= #
+  # 13 entries. Will include taxid, parent_taxid, rank and so forth.
+  # ========================================================================= #
+  attr_accessor :taxid
+  attr_accessor :parent_taxid
+  attr_accessor :rank
+  attr_accessor :embl_code
+  attr_accessor :division_id
+  attr_accessor :inherited_div_flag
+  attr_accessor :genetic_code_id
+  attr_accessor :inherited_gc_flag
+  attr_accessor :mitochondrial_genetic_code_id
+  attr_accessor :inherited_mgc_flag
+  attr_accessor :genbank_hidden_flag
+  attr_accessor :hidden_subtree_root_flag
+  attr_accessor :comments
+
+  # ========================================================================= #
+  # === initialize
+  # ========================================================================= #
+  def initialize(
+      optional_read_in_from_this_file = nil
+    )
+    reset
+    if optional_read_in_from_this_file
+      @data = nodes?(optional_read_in_from_this_file)
+    end
+  end
+
+  # ========================================================================= #
+  # === reset
+  # ========================================================================= #
+  def reset
+    super()
+  end
+
+  # ========================================================================= #
+  # === Node.parse()
+  #
+  # Parse an input string which should be a Node. This method will setup
+  # the corresponding fields.
+  # ========================================================================= #
+  def self.parse(i)
+    _ = split(i.chomp)
+    node = Node.new
+    node.taxid                         = _[0]
+    node.parent_taxid                  = _[1]
+    node.rank                          = _[2]
+    node.embl_code                     = _[3]
+    node.division_id                   = _[4]
+    node.inherited_div_flag            = _[5]
+    node.genetic_code_id               = _[6]
+    node.inherited_gc_flag             = _[7]
+    node.mitochondrial_genetic_code_id = _[8]
+    node.inherited_mgc_flag            = _[9]
+    node.genbank_hidden_flag           = _[10]
+    node.hidden_subtree_root_flag      = _[11]
+    node.comments = sanitize_content(_[12])
+    return node
+  end
+
+  # ========================================================================= #
+  # === parent?
+  # ========================================================================= #
+  def parent? # Give back our parent.
+    parent_taxid
+  end
+
+end
+
+# =========================================================================== #
+# === pad_sql
+#
+# Escape ' characters here.
+# =========================================================================== #
+def pad_sql(i)
+  i = i.gsub(/'/, "\'") if i.include? "'"
+  return i
+end
+
+# =========================================================================== #
+# === pad_properly
+#
+# Input is an Array. We will pad it for a proper SQL query.
+# =========================================================================== #
+def pad_properly(i = "5\t|\tThe domestic cat: perspective on the nature and diversity of cats.\t|\t0\t|\t8603894\t|\t \t|\t\t|\t9685 \t|\n")
+  splitted = split( sanitize(i.chomp) )
+  splitted = splitted.map {|e|
+  begin
+    string = sanitize(e).strip
+    # token = to_utf('|')
+    if string.include? "'"
+      string = string.gsub(/'/, "\'")
+    end
+    return string
+  rescue Exception
+  end
+  }
+  return splitted.join("', '")
+end
+
+end; end

data/lib/bioroebe/taxonomy/parse_fasta.rb

@@ -0,0 +1,383 @@
+#!/usr/bin/ruby -w
+# Encoding: UTF-8
+# frozen_string_literal: true
+# =========================================================================== #
+# === Bioroebe::Taxonomy::ParseFasta
+#
+# The purpose of this class is to parse a fasta file.
+# =========================================================================== #
+require 'bioroebe/base/commandline_application/commandline_application.rb'
+
+module Bioroebe
+
+module Taxonomy # === Bioroebe::Taxonomy
+
+# =========================================================================== #
+# === Bioroebe::Taxonomy::ParseFasta
+# =========================================================================== #
+class ParseFasta < ::Bioroebe::CommandlineApplication # === Bioroebe::Taxonomy::ParseFasta
+
+  require 'bioroebe/taxonomy/shared.rb'
+  require 'bioroebe/taxonomy/info/info.rb' # This is an optional dependency here.
+  require 'bioroebe/calculate/calculate_gc_content.rb'
+
+  # ========================================================================= #
+  # === N_ENTRIES
+  # ========================================================================= #
+  N_ENTRIES = 3 # How many entries will we query to find out that this is a DNA or Protein dataset.
+
+  include Taxonomy::Shared
+
+  # ========================================================================= #
+  # === initialize
+  # ========================================================================= #
+  def initialize(
+      i,
+      run_already = true
+    )
+    reset
+    set_location(i)
+    try_to_read_in_the_dataset
+    run if run_already
+  end
+
+  # ========================================================================= #
+  # === reset
+  # ========================================================================= #
+  def reset
+    super()
+    # ======================================================================= #
+    # === @data
+    # ======================================================================= #
+    @data = nil
+    # ======================================================================= #
+    # === @pointer
+    # ======================================================================= #
+    @pointer = nil
+    # ======================================================================= #
+    # === @hash
+    # ======================================================================= #
+    @hash = {}
+    # ======================================================================= #
+    # === @type
+    # ======================================================================= #
+    @type = nil
+  end
+
+  # ========================================================================= #
+  # === try_to_read_in_the_dataset
+  # ========================================================================= #
+  def try_to_read_in_the_dataset
+    @data = File.read(@location) if File.exist?(@location)
+  end
+
+  # ========================================================================= #
+  # === set_location
+  #
+  # This method sets the base location of our input-file.
+  # ========================================================================= #
+  def set_location(i = nil)
+    i = i.first if i.is_a? Array # For now, use only the first element, if it is an Array.
+    i = i.to_s
+    if i =~ /^\d+$/ # if the input consists of only numbers.
+      i = Dir['*'][i.to_i - 1]
+    end
+    unless File.exist? i # try a rescue in this case.
+      i = AA_DIR+File.basename(i)
+    end
+    # ===================================================================== #
+    # Expand to the proper path next:
+    # ===================================================================== #
+    i = return_pwd+i unless i.include? '/'
+    @location = i
+  end
+
+  # ========================================================================= #
+  # === report_one_sequence
+  # ========================================================================= #
+  def report_one_sequence
+    _ = sequence.first # sequence() is a method call.
+    show_n_characters = 45
+    if _
+      if Bioroebe.do_truncate? and (_.size > show_n_characters+1)
+        _ = _[0, show_n_characters]+' [TRUNCATED]'
+      end
+      e 'The (at least one) sequence is: '+sfancy(_)
+    else
+      e 'We could not find any sequence.'
+    end
+  end
+
+  # ========================================================================= #
+  # === try_to_locate_info_file
+  # ========================================================================= #
+  def try_to_locate_info_file(i = @location)
+    i = File.basename(i)
+    # chop away the extname.
+    i.gsub!(/#{File.extname(i)}/, '')
+    i.gsub!(/_pep/,'') if i.include? '_pep'
+    _ = INFO_DIR+i+'*'
+    results = Dir[_]
+    if results.empty?
+      e 'Could not find any entry for '+sfancy(_)+'.'
+    else
+      pp results
+      data = Info.parse(results.first)
+      if data.taxonomy_id
+        set_pgpassword
+        # Next, find out the tax ID through a postgre query:
+        _ = ''.dup
+        _ << POSTGRE_LOGIN_COMMAND
+        _ << ' --command="'
+        _ << 'select * from names where tax_id='+data.taxonomy_id+' LIMIT 15;"'
+        esystem _
+      end
+    end
+  end
+
+  # ========================================================================= #
+  # === hash?
+  # ========================================================================= #
+  def hash? # getter method for the @hash dataset.
+    @hash
+  end; alias hash hash? # === hash
+
+  # ========================================================================= #
+  # === report_how_many_entries_exist
+  # ========================================================================= #
+  def report_how_many_entries_exist
+    n_entries = @hash.keys.size
+    e 'We have '+sfancy(n_entries)+' Fasta entries (subsections) '\
+      'in the file '+sfile(@location)+'.'
+  end
+
+  # ========================================================================= #
+  # === report_filesize
+  # ========================================================================= #
+  def report_filesize
+    e 'The filesize of '+sfile(@location)+' is '+
+      sfancy(filesize)+' Bytes.'
+  end
+
+  # ========================================================================= #
+  # === filesize
+  # ========================================================================= #
+  def filesize(i = @location)
+    File.size?(i).to_s
+  end
+
+  # ========================================================================= #
+  # === report_last_modification_time
+  # ========================================================================= #
+  def report_last_modification_time
+    e 'The file was last modified at '+simp(modification_time)
+  end
+ 
+  # ========================================================================= #
+  # === modification_time
+  #
+  # We will return the german-variant for the time.
+  # ========================================================================= #
+  def modification_time
+    File.mtime(@location).strftime('%H:%M:%S, %d.%m.%Y')
+  end
+
+  # ========================================================================= #
+  # === debug
+  # ========================================================================= #
+  def debug
+    pp @hash
+    pp @hash.keys.size
+  end
+
+  # ========================================================================= #
+  # === sequence
+  #
+  # By default, this method will feedback one entry, the first entry.
+  # We can however pass another number, in which case we will return
+  # more than one entry.
+  # ========================================================================= #
+  def sequence(return_n_entries = 1)
+    result = []
+    if return_n_entries == 1 # the default
+      result << @hash[@hash.keys.first]
+    else
+      return_n_entries.times {
+        result << @hash[@hash.keys.sample]
+      }
+    end
+    return result
+  end
+
+  # ========================================================================= #
+  # === sequence_and_accession_number
+  #
+  # This method is similar to the above method called sequence(), but it
+  # also returns the accession number of the fasta file.
+  # ========================================================================= #
+  def sequence_and_accession_number(i = 3)
+    result = []
+    i.times {
+      this_key   = @hash.keys.sample
+      this_value = @hash[this_key]
+      result << [this_key, this_value]
+    }
+    return result
+  end
+
+  # ========================================================================= #
+  # === report_whether_it_is_nt_or_proteine
+  #
+  # We find out whether we have NT data or proteine (polypeptide) data.
+  # For this to determine, we will have to make use of another class.
+  #
+  # Also note that for this method to correctly work, we must call the
+  # method is_it_dna_or_protein? first.
+  # ========================================================================= #
+  def report_whether_it_is_nt_or_proteine
+    n_entries = N_ENTRIES.to_s
+    n_entries = @hash.keys.size if n_entries.to_i > @hash.keys.size
+    joined_accession_numbers = @only_accession_numbers.each_with_index.map { |element, index|
+      ['('+lightblue((index + 1).to_s)+') '+element]
+    }.flatten.join(pink(' / '))
+    e 'We assume that this dataset is '+sfancy(@type)+'. This conclusion '\
+      'is based on analyzing/checking '
+    e simp(n_entries)+' different entries (subsections) in the file '+
+      sfile(File.basename(@location))+', for a total of '+sfancy(@total_characters)+' '+
+      'characters (=tokens) (the '+simp(n_entries)+' Accession Numbers that were '+
+      'checked are: '+joined_accession_numbers+').'
+    e 'The allowed entries for DNA-sequences that we used for this assessment were: '+
+      simp(IsDNA::ARRAY_VALID_SEQUENCES.join(', '))
+    if Object.const_defined? :CalculateGCContent # Query the GC content here.
+      e 'The percentage of the GC content is: '
+      CalculateGCContent.new(@only_sequences).report
+    end if @type == 'DNA' # Feedback this part here only if we work with DNA.
+  end
+
+  # ========================================================================= #
+  # === is_it_dna_or_protein?
+  #
+  # This method sets the @type variable. It makes use of class IsDNA for
+  # this.
+  # ========================================================================= #
+  def is_it_dna_or_protein?
+    these_entries = sequence_and_accession_number(N_ENTRIES) # sequence() is a method call defined above.
+    # Transpose the array next.
+    transposed = these_entries.transpose
+    @only_accession_numbers = transposed[0]
+    @only_sequences = transposed[1]
+    _ = IsDNA.new(@only_sequences)
+    if _.is_dna?
+      @type = 'DNA'
+    else
+      @type = 'Protein'
+    end
+    @total_characters = _.total_characters
+  end
+
+  # ========================================================================= #
+  # === ParseFasta.batch
+  # ========================================================================= #
+  def self.batch_process(from_this_directory = AA_DIR)
+    e 'We will now process all fasta files from directory '+
+      sdir(from_this_directory)+'.'
+    entries = Dir[from_this_directory+'*.fa']
+    e 'There are '+sfancy(entries.size.to_s)+' entries in '\
+      'that directory.'+N+N
+    entries.each {|entry|
+      cliner
+      e
+      _ = ParseFasta.new(entry)
+      _.report_status
+      _.try_to_locate_info_file
+      e
+    }
+    e 'Finished!'
+  end
+
+  # ========================================================================= #
+  # === all_accession_entries
+  #
+  # Return all accession entries here.
+  # ========================================================================= #
+  def all_accession_entries
+    @hash.keys
+  end
+
+  # ========================================================================= #
+  # === n_entries
+  # ========================================================================= #
+  def n_entries
+    all_accession_entries.size
+  end
+
+  # ========================================================================= #
+  # === status?                                                (status tag)
+  #
+  # We report some data about the dataset.
+  #
+  # This is useful for finding out about:
+  #
+  #   (1) how many entries exist in our fasta file
+  #   (2) when the file was last modified
+  #   (3) how big the file is
+  #
+  # ========================================================================= #
+  def status?
+    report_how_many_entries_exist
+    report_last_modification_time
+    report_filesize
+    report_whether_it_is_nt_or_proteine
+  end; alias report_status status? # === report_status
+       alias report        status? # === report
+
+  # ========================================================================= #
+  # === location?
+  # ========================================================================= #
+  def location?
+    @location
+  end; alias location location? # === location
+
+  # ========================================================================= #
+  # === type?
+  # ========================================================================= #
+  def type?
+    @type
+  end; alias type type? # === type
+
+  # ========================================================================= #
+  # === run_everything
+  # ========================================================================= #
+  def run_everything
+    if @data
+      @data.split("\n").each {|entry|
+        entry.chomp!
+        if entry.include? '>' # This is a Description line.
+          @pointer = entry.delete('>')
+          @hash[@pointer] = ''.dup
+        else
+          @hash[@pointer] << entry unless @hash[@pointer].nil?
+        end
+      } 
+      is_it_dna_or_protein?
+    end
+  end
+
+  # ========================================================================= #
+  # === run                                                         (run tag)
+  # ========================================================================= #
+  def run
+    begin
+      run_everything
+    rescue Interrupt
+      e
+      e 'User requested exit. Thus exiting now gracefully.'
+      exit
+    end
+  end
+
+end; end; end
+
+if __FILE__ == $PROGRAM_NAME
+  puts Bioroebe::Taxonomy::ParseFasta.new(ARGV)
+end